Development of a Mobile App for Point-of-Care Rapid Blood Test Result Interpretation

Thesis Abstract

The timely and accurate interpretation of rapid blood test results at the point of care remains a critical challenge in enhancing diagnostic efficiency and patient outcomes, especially in resource-limited settings where healthcare providers often lack immediate access to specialized laboratory expertise. This study aims to develop a mobile application that facilitates automated, reliable, and user-friendly interpretation of point-of-care rapid blood test results. Specifically, the research objectives encompass designing and implementing the mobile app, evaluating its usability among healthcare providers, and assessing its accuracy and diagnostic consistency compared to conventional manual interpretation. A mixed-methods research design was employed, integrating quantitative and qualitative approaches to ensure comprehensive evaluation. The study population comprised 150 healthcare practitioners—including nurses, laboratory technicians, and clinicians—from primary healthcare clinics in a metropolitan healthcare district. Using stratified random sampling, a sample of 100 practitioners was selected for usability testing, while an additional 50 practitioners participated in focus group discussions to explore contextual factors affecting app adoption and use. Data collection instruments included a structured questionnaire to gather demographic data, usability assessment scales such as the System Usability Scale (SUS), and clinical vignettes for evaluating interpretation accuracy. The app prototype was developed based on current diagnostic algorithms and integrated with a user interface aligned with existing mobile operating systems. The software incorporated decision support features based on established clinical guidelines. To validate the app's interpretative accuracy, test results from the mobile app were compared against standard laboratory reports and manual interpretations using Bland-Altman analysis and Cohen’s kappa coefficient to assess agreement and reliability. Quantitative data were analyzed through descriptive statistics, t-tests, and regression analysis to determine usability scores and factors influencing app performance. The qualitative data from focus groups underwent thematic analysis, providing insights into user perceptions, barriers to adoption, and suggestions for improvement. The app's diagnostic accuracy was evaluated through sensitivity, specificity, and predictive value calculations, with ROC curve analysis used to assess overall discriminative ability. Expected findings predict that the mobile app will demonstrate high usability scores (mean SUS above 80), with significant agreement (kappa > 0.8) between app-based interpretations and standard laboratory reports. The app is anticipated to reduce interpretation errors, increase speed, and improve confidence among healthcare workers in resource-constrained environments. Further, qualitative insights are expected to reveal crucial facilitators and barriers for adoption, including factors related to digital literacy, infrastructure, and workflow integration. This research contributes novel evidence demonstrating that mobile health (mHealth) applications can effectively augment point-of-care diagnostics by providing rapid, accurate, and accessible interpretation support. It advances knowledge on integrating decision support systems within mobile platforms for laboratory testing, particularly in low-resource settings. The study highlights the potential for such technology to enhance diagnostic precision, optimize clinical decision-making, and ultimately improve patient care outcomes. Concluding, the findings advocate for wider implementation of mobile app-based solutions in laboratory medicine, recommending routine validation and training to maximize impact. Future research should explore longitudinal effects of app adoption on patient outcomes and scalability across diverse healthcare contexts. The development of this mobile app represents a significant step toward leveraging digital health innovations to address existing gaps in diagnostic precision and healthcare delivery at the point of care.